Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +32 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/May22_16-18-09_bc4270970810/1653236329.533225/events.out.tfevents.1653236329.bc4270970810.81.1 +3 -0
- runs/May22_16-18-09_bc4270970810/1653236345.9524891/events.out.tfevents.1653236345.bc4270970810.81.2 +3 -0
- runs/May22_16-18-09_bc4270970810/1653236396.2706394/events.out.tfevents.1653236396.bc4270970810.81.3 +3 -0
- runs/May22_16-18-09_bc4270970810/events.out.tfevents.1653236329.bc4270970810.81.0 +3 -0
- runs/May22_16-20-53_bc4270970810/1653236470.0561447/events.out.tfevents.1653236470.bc4270970810.81.5 +3 -0
- runs/May22_16-20-53_bc4270970810/events.out.tfevents.1653236470.bc4270970810.81.4 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-07,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"max_relative_positions": -1,
|
| 15 |
+
"model_type": "deberta",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"pooler_dropout": 0,
|
| 20 |
+
"pooler_hidden_act": "gelu",
|
| 21 |
+
"pooler_hidden_size": 768,
|
| 22 |
+
"pos_att_type": [
|
| 23 |
+
"c2p",
|
| 24 |
+
"p2c"
|
| 25 |
+
],
|
| 26 |
+
"position_biased_input": false,
|
| 27 |
+
"relative_attention": true,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.19.2",
|
| 30 |
+
"type_vocab_size": 0,
|
| 31 |
+
"vocab_size": 50265
|
| 32 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ded08a5394ed126fee76614646d0117518138f325f295c8d99d59940c9fe4b2b
|
| 3 |
+
size 554483891
|
runs/May22_16-18-09_bc4270970810/1653236329.533225/events.out.tfevents.1653236329.bc4270970810.81.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6478d6e8cd48f3c1a270205cdb458e0d4e517f27cac7969e0d5993330a776421
|
| 3 |
+
size 5196
|
runs/May22_16-18-09_bc4270970810/1653236345.9524891/events.out.tfevents.1653236345.bc4270970810.81.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:727e18ecad6d655ee83c7df991d74c93c3065907ede0fe68c7bfbe80cf0d8fa9
|
| 3 |
+
size 5196
|
runs/May22_16-18-09_bc4270970810/1653236396.2706394/events.out.tfevents.1653236396.bc4270970810.81.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4323ac7b87d106d76fda9628405abd82444faaee5de2b3d69282406473f7c3f
|
| 3 |
+
size 5196
|
runs/May22_16-18-09_bc4270970810/events.out.tfevents.1653236329.bc4270970810.81.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dea37369201d4d781c8861ec47a4bcb20f9d59e5ae8443b0a70140488da710b1
|
| 3 |
+
size 10720
|
runs/May22_16-20-53_bc4270970810/1653236470.0561447/events.out.tfevents.1653236470.bc4270970810.81.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e262401cb20a246f6f5c7df0c8ccb0a4767f468f595b03a4cfeefc4792de27c
|
| 3 |
+
size 5196
|
runs/May22_16-20-53_bc4270970810/events.out.tfevents.1653236470.bc4270970810.81.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7c68892bff328b3083dd050d0986c901d0b5e0863d56a9446c8744ef7b743d9
|
| 3 |
+
size 3757
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": {"content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "do_lower_case": false, "vocab_type": "gpt2", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "microsoft/deberta-base", "add_bos_token": false, "tokenizer_class": "DebertaTokenizer"}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9462677aeb9976dc3f7bbf06de7d2fa00ee3e5e9f1609d78fa25a2ee4407b84
|
| 3 |
+
size 3247
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|